存储高级 数据保护技术DDP说明
1
SANtricity RAID Protection
Host LUNs Volumes Volume Groups SSDs
Volume groups
– RAID 0, 1, 10, 5, 6 – Intermix RAID levels – Various group sizes
RAID-6
SSDs operated independently with user data and redundant information (dual parity) are striped across the SSDs. The equivalent capacity of two SSDs is used for redundant information. 5 30 60% to 93% IOPS | MB/s Good for reads, small IOPS, many concurrent IOPS and random I/Os. Parity utilizes small portion of raw capacity. Writes are particularly demanding
NetApp Confidential
11
DDP: Simplicity, Performance, Protection
Simplified administration
―With Dynamic Disk Pools, you can add or lose disk drives without impact, reconfiguration, or headaches.‖
Combining effort: All drives in the pool sustain the workload— perfect for virtual mixed workloads or fast reconstruction if needed.
Large pool of spindles for every volume reduces hot spots
Each volume spread across all drives in pool
Dynamic distribution/redistribution is a nondisruptive background operation
Performance drop is minimized following drive failure Dynamic rebalance completes up to 8x faster than traditional RAID in random environments and up to 2x faster in sequential environments
– All drives are active (no idle hot spares) – Spare capacity is available to all volumes
Data is dynamically recreated/redistributed whenever pools grows or shrinks
2 System max 50% IOPS Performance as multiple requests can be fulfilled simultaneously. Also offers the highest data availability Storage costs are doubled
RAID 0 – striped
Data Data Data Data
RAID 1 (10) – mirrored and striped
Data Data disks and rotating parity
Data Data Data Data Data Parity Parity Data
24-drive system with 2 10-drive groups (8+2) and 4 hot spares
5
The Problem
The Large-Disk-Drive Challenge
Staggering amounts of data to store, protect, access
4TB+
Larger drives equal longer rebuilds—anywhere from 10+ hours to several days
6
Dynamic Disk Pools
Maintain SLAs during drive failure
Stay in the green
Some sites have thousands of large-capacity drives Drive failures are continual, particularly with NL-SAS drives
Production I/O is impacted during rebuilds
Hot spares sit idle until a drive fails
24-drive system with 2 10-drive groups (8+2) and 4 hot spares
4
Traditional RAID—Drive Failure
Data is reconstructed onto hot spare
Advantages
Performance due to parallel operation of the access
No redundancy. One drive fails, data is lost
Disadvantages
Dynamic Disk Pools Overview
DDP dynamically distributes data, spare capacity, and parity information across a pool of SSDs
Flexible: Add ANY* number of drives for additional capacity— system automatically rebalances data for optimal performance.
* After the minimum of 11.
8
Data Rebalancing in Minutes vs. Days
NetApp Confidential
3 30 67% to 97% IOPS | MB/s Good for reads, small IOPS, many concurrent IOPS and random I/Os. Parity utilizes small portion of raw capacity. Writes are particularly demanding
RAID 6 (P+Q) – data disks and rotating dual parity
Data Data Data Data Data Parity Parity Q Parity Q Parity Data
Data
Parity
Q Parity
Data
Data
Block-level striping with a distributed parity
Performance Impact of a Disk Failure
Maintain business SLAs with a drive failure
Optimal Acceptable
120 100
DDP
RAID 6
Performance
80
RAID
Time
DDP
60
2.5 Days
More than 4 Days
7
Traditional Dynamic RAID Technology Innovative Disk Pools
Balanced: Algorithm randomly spreads data across all drives, balancing workload and rebuilding if necessary. Easy: No RAID or idle spares to manage— active spare capacity on all drives.
10
Description
Data is striped across multiple SSDs.
Min # of SSDs Max # of SSDs Usable capacity as % of raw capacity Application
1 System max 100% IOPS | MB/s
RAID-5
SSDs operated independently with user data and redundant information (parity) are striped across the SSDs. The equivalent capacity of one SSD is used for redundant information.
Single drive responsible for all writes (bottleneck) Reconstruction happens linearly (one stripe at a time)
All volumes in that group are significantly impacted